Babak Karasfi | Universiti Teknologi PETRONAS (original) (raw)

Papers by Babak Karasfi

Journal of Ambient Intelligence and Humanized Computing, 2012

Sensor-based human activity recognition can benefit a variety of applications such as health care... more Sensor-based human activity recognition can benefit a variety of applications such as health care, fitness, smart homes, rehabilitation training, and so forth. In this paper, we propose a novel two-layer diversity-enhanced multiclassifier recognition method for single wearable accelerometer-based human activity recognition, which contains data-based and classifier-based diversity enhancement. Firstly, we introduce the kernel Fisher discriminant analysis (KFDA) technique to spatially transform the training samples and enhance the discrimination between activities. In addition, bootstrap resampling is utilized to increase the diversities of the dataset for training the base classifiers in the multiclassifier system. Secondly, a combined diversity measure for selecting the base classifiers with excellent performance and large diversity is proposed to optimize the performance of the multiclassifier system. Lastly, majority voting is utilized to combine the preferred base classifiers. Experiments showed that the data-based diversity enhancement can improve the discriminance of different activity samples and promote the generation of base classifiers with different structures and performances. Compared with random selection and traditional ensemble methods, including Bagging and Adaboost, the proposed method achieved 92.3% accuracy and 90.7% recall, which demonstrates better performance in activity recognition.

Measurement, 2019

The paper presents a feasibility study for heart rate measurement using a digital camera to perfo... more The paper presents a feasibility study for heart rate measurement using a digital camera to perform health monitoring. The feasibility study investigates the reliability of the state of the art heart rate measuring methods in realistic situations. Therefore, an experiment was designed and carried out on 45 subjects to investigate the effects caused by illumination, motion, skin tone, and distance variance. The experiment was conducted for two main scenarios; human-computer interaction scenario and health monitoring scenario. The human-computer scenario investigated the effects caused by illumination variance, motion variance, and skin tone variance. The health monitoring scenario investigates the feasibility of health monitoring at public spaces (i.e. airports, subways, malls). Five state of the art heart rate measuring methods were re-implemented and tested with the feasibility study database. The results were compared with ground truth to estimate the heart rate measurement error. The heart rate measurement error was analyzed using mean error, standard deviation; root means square error and Pearson correlation coefficient. The findings of this experiment inferred promising results for health monitoring of subjects standing at a distance of 500 cm.

2015 IEEE Student Symposium in Biomedical Engineering & Sciences (ISSBES), 2015

Computer assisted diagnosis systems (CADs) is now commonly used as a second opinion to help radio... more Computer assisted diagnosis systems (CADs) is now commonly used as a second opinion to help radiologists in image interpretation by emphasizing on the suspicious areas. Segmentation of region of interests in 2-dimensional (2D) or volume of interests in 3dimensional (3D) images is a critical step in CAD systems. 3D image segmentation using 2D slices has been a keen of interest for research purpose. In this paper we propose to reconstruct a 3D form of volume of interests (VOIs) from a series of 2D images in computed tomography laser mammography (CTLM). In this paper, a 3D Fuzzy C-Means clustering have been implemented to reconstruct VOIs for breast cancer detection in CTLM images. To assess the accuracy of the extracted VOIs against ground truth, percentage error factor is used and produced error value of 10.72% in our dataset of 62 CTLM breast images collected among Malaysian participants.

2015 IEEE International Conference on Automation Science and Engineering (CASE), 2015

This paper introduces a new hybrid control architecture for solving the navigation problem of mob... more This paper introduces a new hybrid control architecture for solving the navigation problem of mobile robot in an unknown dynamic environment based on an actual-virtual target switching strategy. This hybrid architecture is a combination of deliberative and reactive architectures which consists of three layers: modeling, planning and reaction. The deliberative architecture produces collision-free with shortest-distance path, while using the reactive architecture generates safe and time minimal navigation path. The proposed approach differs from previous ones in its integration architecture, the control techniques implemented in each module, and interfaces between the deliberative and reactive components. Validity and feasibility of the proposed approach are verified through simulation and real robot experiments.

2017 Artificial Intelligence and Robotics (IRANOPEN), 2017

Quadratic assignment problems one of combinatorial optimization problems that pays to number of f... more Quadratic assignment problems one of combinatorial optimization problems that pays to number of facilities to number of places. The objective is to minimize the cost. QAP is one of the degree of complexity of hard problems deterministic algorithms are able to solve smaller sample problem. Fast local search used to solve qap. but despite the wider space exploration. There are not certain views for better search. The objective is to provide a way to be able find a visual representation of the search space Which leads to reduced method efficiency and in cases where the distance between the points searched was a great gap as much as possible to find areas that are not searched and evaluated. The new proposed method is able to decrease average best answer fast local search algorithm from 0.65 percent to 0.26 percent and so will have a better exploration of space search. Review its performance based on standard test functions and compare it with fast local search algorithm represent quali...

Abstract. This paper presents an overview of the MRL small size robotic team. This paper describe... more Abstract. This paper presents an overview of the MRL small size robotic team. This paper describes three of the main changes to the MRL RoboCup team which lead us to Smart Start. The first part explains the advantages which E-League had for undergraduate students. The second part covers the electrical, mechanical and control parts of robot. Next part describes our development on a new Vision system using smart scanning technique. Moreover, a robust filter on variable lighting condition and path planning improvement based on potential filed algorithm. Finally, the last part introduces MRL 3D Simulator which developed to investigate the control commands. 1 Introduction The Azad University of Qazvin’s MRL RoboCup team established due to research in Mechatronics and Robotics in Mechatronics Research Laboratory. A year of hard effort leads to qualification in E-League competition. Although we missed the game but E-League experiences was a fairly good initiation to construct our small siz...

Breast cancer is the foremost common invasive cancer among ladies and is the primary cause of mor... more Breast cancer is the foremost common invasive cancer among ladies and is the primary cause of mortality from cancer around the world. To avoid the tall mortality, early detection and treatment are essential. Breast screening which uses noninvasive manner to assess tissue properties plays an imperative role in early designation. In any case, the huge information volume makes the examination become long, time-consuming and inoperable. Machine learning techniques and image processing are trending to investigate different tissue characterization and tumor appearance in radiology for automatic malignancy classification. This paper provide comparison of two supervised classification techniques for angiogenesis detection in computed tomography laser mammography image which is the major sign of high hemoglobin concentration and breast cancer.

2018 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium

Reinforcement learning is a subfield of machine learning which is similar to human learning. In r... more Reinforcement learning is a subfield of machine learning which is similar to human learning. In recent years, it has drawn a considerable portion of researchers' attention and it has been revolutionized; such as its integration with deep learning. This integration has created a better understanding of the visual environments and end-to-end direct learning from pixels to solve problems that have previously been intractable. This improvement has led to the creation of various deep reinforcement learning algorithms with different goals. In this paper, deep reinforcement learning algorithms and their applications are reviewed and categorized. This work also addresses the advantages and disadvantages of algorithms and the challenges that are solved with appearance of deep reinforcement learning. In order to use these algorithms, there are important considerations that need to be addressed in each problem. These considerations are about the most important components of reinforcement learning, which has been analyzed and categorized as the important achievement of this paper.

2018 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium

In Recent years, Representation learning as one of the information extraction and data mapping me... more In Recent years, Representation learning as one of the information extraction and data mapping methods in machine learning systems has received huge attention. Artificial deep neural networks are considered as one of the basic structures capable of representation learning. However, a large number of standard representation learning methods are supervised and requires a lot of labeled data. In this paper, we introduce an unsupervised representation learning by designing and implementing deep neural networks (DNNs) in combination with Generative Adversarial Networks (GANs). The main idea behind the proposed method, which causes the superiority of this method over others is representation learning via the generative models and encoder networks altogether. In this research, encoders are utilized in addition to the generative models to help the more features to be extracted. It is shown that the proposed method not only help feature extraction but accelerate and improve the performance of the learning in GANs which lead to better feature extraction. The results confirm the superiority of the proposed approach regarding classification accuracy by 2% to 6% improvement over other unsupervised feature learning methods.

Biomedical Signal Processing and Control

Abstract Photoplethysmography and Ballistocardiography are two concepts that are used to measure ... more Abstract Photoplethysmography and Ballistocardiography are two concepts that are used to measure heart rate from human, by using facial videos. Heart rate estimation is essential to determine the physiological and pathological state of a person. This paper presents a critical review of digital camera based heart rate estimating method on facial skin. This review extends the investigation on to the principles and theory behind photoplethysmography and ballistocardiography. The article contains reviews on the significance of the methods and contributions to overcome challenges such as; poor signal strength, illumination variance, and motion variance. The experiments were conducted to validate the state of the art methods on a challenging database that is available publicly. The implemented methods were validated using the database, on 27 subjects for a range of skin tones from pearl white, fair, olive to black. The results were computed using statistical methods such as: mean error, standard deviation, the root mean square error, Pearson correlation coefficient, and Bland-Altman analysis. The results derived from the experiments showed the reliability of the state of the art methods and provided direction to improve for situations involving illumination variance and motion variance.

Journal of digital imaging, Jan 20, 2017

Computed tomography laser mammography (Eid et al. Egyp J Radiol Nucl Med, 37(1): p. 633-643, 1) i... more Computed tomography laser mammography (Eid et al. Egyp J Radiol Nucl Med, 37(1): p. 633-643, 1) is a non-invasive imaging modality for breast cancer diagnosis, which is time-consuming and challenging for the radiologist to interpret the images. Some issues have increased the missed diagnosis of radiologists in visual manner assessment in CTLM images, such as technical reasons which are related to imaging quality and human error due to the structural complexity in appearance. The purpose of this study is to develop a computer-aided diagnosis framework to enhance the performance of radiologist in the interpretation of CTLM images. The proposed CAD system contains three main stages including segmentation of volume of interest (VOI), feature extraction and classification. A 3D Fuzzy segmentation technique has been implemented to extract the VOI. The shape and texture of angiogenesis in CTLM images are significant characteristics to differentiate malignancy or benign lesions. The 3D comp...

EXCLI journal, 2017

Breast cancer is the most prevalent cancer that affects women all over the world. Early detection... more Breast cancer is the most prevalent cancer that affects women all over the world. Early detection and treatment of breast cancer could decline the mortality rate. Some issues such as technical reasons, which related to imaging quality and human error, increase misdiagnosis of breast cancer by radiologists. Computer-aided detection systems (CADs) are developed to overcome these restrictions and have been studied in many imaging modalities for breast cancer detection in recent years. The CAD systems improve radiologists' performance in finding and discriminating between the normal and abnormal tissues. These procedures are performed only as a double reader but the absolute decisions are still made by the radiologist. In this study, the recent CAD systems for breast cancer detection on different modalities such as mammography, ultrasound, MRI, and biopsy histopathological images are introduced. The foundation of CAD systems generally consist of four stages: Pre-processing, Segmenta...

2016 6th International Conference on Intelligent and Advanced Systems (ICIAS), 2016

This paper presents a feasibility study on heart rate detection using a digital camera. The paper... more This paper presents a feasibility study on heart rate detection using a digital camera. The paper investigates the possibility of Heart rate detection for individuals far from the camera sensor. The study is done to exploit the feasibility for heart rate estimation using a digital camera to enables health monitoring in visual surveillance. An experiment was conducted using 14 healthy subjects of various skin tones. State of the art heart rate estimation methods from photoplethysmography and ballistocardiography was implemented. The method were experimented on videos of subjects that were standing away 5 meters from the camera. Results derived showed that the technology has many challenges are to be overcome. The effect of ambient light variation, involuntary artifact movement, and poor signal to noise ratio are some of the problems to be addressed.

2016 Artificial Intelligence and Robotics (IRANOPEN), 2016

Road detection from a single image is a challenging problem. In this paper, a new color feature b... more Road detection from a single image is a challenging problem. In this paper, a new color feature based on road detection method has been introduced. The proposed method utilized color features to learn and estimate the road straight part and provide vanishing points. In order to extract the road area, a combination of new learned color features and vanishing point algorithm have been used that can be released as the proposed method contribution. The experimental results show the efficiency of new method and Obtained results; Recall 92%, F-Measure 84% and accuracy 90% are compared with existing methods which show superiority of the proposed method.

2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings, 2016

This paper presents an optimal selection on the region of interest (ROI) and color spaces to extr... more This paper presents an optimal selection on the region of interest (ROI) and color spaces to extract photoplethysmography signals from facial videos. The study is carried out under two sections; ROI selection and color space selection. We compared five different ROI selection for different regions of the face. We also investigated three color spectrums namely additive, perceptual and orthogonal color spaces. The study experimented on the publicly available human-computer interaction (HCI) database. When evaluated on 30 subjects, the results showed that the ROI selection on the forehead and the green spectrum of the additive color space to provides higher accuracy for heart rate measurement.

2015 IEEE Student Symposium in Biomedical Engineering & Sciences (ISSBES), 2015

Video scene of real world crowd movement present great challenges for real-time visual surveillan... more Video scene of real world crowd movement present great challenges for real-time visual surveillance system. This paper presents a framework that detects and cluster dominant crowd flow field into region of interest from a video sequence. A particle dynamic system is applied on the video scene represented by optical flow features obtained based on classical-NL technique. Time integration of the system gives the individual particle motion trajectory. The collection of motion trajectories gives the region of interest. We obtained the segmented dominant flow regions by clustering the region of interest. The clustering of flow field may indicate the possible presence of instability in the segmented regions. Performances of different clustering techniques are compared in this study. Comparison of classification accuracy, precision, recall and F-measures are reported. Different boundaries of flow segments are detected. A change observed on segmented flow field is considered as anomaly. The experiments are carried out on publicly available datasets of crowd.

This paper presents an overview of the MRL small size robotic team. This paper describes three of... more This paper presents an overview of the MRL small size robotic team. This paper describes three of the main changes to the MRL RoboCup team which lead us to Smart Start. The first part explains the advantages which E-League had for undergraduate students. The second part covers the electrical, mechanical and control parts of robot. Next part describes our development on a new Vision system using smart scanning technique. Moreover, a robust filter on variable lighting condition and path planning improvement based on potential filed algorithm. Finally, the last part introduces MRL 3D Simulator which developed to investigate the control commands.

Journal of Ambient Intelligence and Humanized Computing, 2012

Sensor-based human activity recognition can benefit a variety of applications such as health care... more Sensor-based human activity recognition can benefit a variety of applications such as health care, fitness, smart homes, rehabilitation training, and so forth. In this paper, we propose a novel two-layer diversity-enhanced multiclassifier recognition method for single wearable accelerometer-based human activity recognition, which contains data-based and classifier-based diversity enhancement. Firstly, we introduce the kernel Fisher discriminant analysis (KFDA) technique to spatially transform the training samples and enhance the discrimination between activities. In addition, bootstrap resampling is utilized to increase the diversities of the dataset for training the base classifiers in the multiclassifier system. Secondly, a combined diversity measure for selecting the base classifiers with excellent performance and large diversity is proposed to optimize the performance of the multiclassifier system. Lastly, majority voting is utilized to combine the preferred base classifiers. Experiments showed that the data-based diversity enhancement can improve the discriminance of different activity samples and promote the generation of base classifiers with different structures and performances. Compared with random selection and traditional ensemble methods, including Bagging and Adaboost, the proposed method achieved 92.3% accuracy and 90.7% recall, which demonstrates better performance in activity recognition.

Measurement, 2019

The paper presents a feasibility study for heart rate measurement using a digital camera to perfo... more The paper presents a feasibility study for heart rate measurement using a digital camera to perform health monitoring. The feasibility study investigates the reliability of the state of the art heart rate measuring methods in realistic situations. Therefore, an experiment was designed and carried out on 45 subjects to investigate the effects caused by illumination, motion, skin tone, and distance variance. The experiment was conducted for two main scenarios; human-computer interaction scenario and health monitoring scenario. The human-computer scenario investigated the effects caused by illumination variance, motion variance, and skin tone variance. The health monitoring scenario investigates the feasibility of health monitoring at public spaces (i.e. airports, subways, malls). Five state of the art heart rate measuring methods were re-implemented and tested with the feasibility study database. The results were compared with ground truth to estimate the heart rate measurement error. The heart rate measurement error was analyzed using mean error, standard deviation; root means square error and Pearson correlation coefficient. The findings of this experiment inferred promising results for health monitoring of subjects standing at a distance of 500 cm.

2015 IEEE Student Symposium in Biomedical Engineering & Sciences (ISSBES), 2015

Computer assisted diagnosis systems (CADs) is now commonly used as a second opinion to help radio... more Computer assisted diagnosis systems (CADs) is now commonly used as a second opinion to help radiologists in image interpretation by emphasizing on the suspicious areas. Segmentation of region of interests in 2-dimensional (2D) or volume of interests in 3dimensional (3D) images is a critical step in CAD systems. 3D image segmentation using 2D slices has been a keen of interest for research purpose. In this paper we propose to reconstruct a 3D form of volume of interests (VOIs) from a series of 2D images in computed tomography laser mammography (CTLM). In this paper, a 3D Fuzzy C-Means clustering have been implemented to reconstruct VOIs for breast cancer detection in CTLM images. To assess the accuracy of the extracted VOIs against ground truth, percentage error factor is used and produced error value of 10.72% in our dataset of 62 CTLM breast images collected among Malaysian participants.

2015 IEEE International Conference on Automation Science and Engineering (CASE), 2015

This paper introduces a new hybrid control architecture for solving the navigation problem of mob... more This paper introduces a new hybrid control architecture for solving the navigation problem of mobile robot in an unknown dynamic environment based on an actual-virtual target switching strategy. This hybrid architecture is a combination of deliberative and reactive architectures which consists of three layers: modeling, planning and reaction. The deliberative architecture produces collision-free with shortest-distance path, while using the reactive architecture generates safe and time minimal navigation path. The proposed approach differs from previous ones in its integration architecture, the control techniques implemented in each module, and interfaces between the deliberative and reactive components. Validity and feasibility of the proposed approach are verified through simulation and real robot experiments.

2017 Artificial Intelligence and Robotics (IRANOPEN), 2017

Quadratic assignment problems one of combinatorial optimization problems that pays to number of f... more Quadratic assignment problems one of combinatorial optimization problems that pays to number of facilities to number of places. The objective is to minimize the cost. QAP is one of the degree of complexity of hard problems deterministic algorithms are able to solve smaller sample problem. Fast local search used to solve qap. but despite the wider space exploration. There are not certain views for better search. The objective is to provide a way to be able find a visual representation of the search space Which leads to reduced method efficiency and in cases where the distance between the points searched was a great gap as much as possible to find areas that are not searched and evaluated. The new proposed method is able to decrease average best answer fast local search algorithm from 0.65 percent to 0.26 percent and so will have a better exploration of space search. Review its performance based on standard test functions and compare it with fast local search algorithm represent quali...

Abstract. This paper presents an overview of the MRL small size robotic team. This paper describe... more Abstract. This paper presents an overview of the MRL small size robotic team. This paper describes three of the main changes to the MRL RoboCup team which lead us to Smart Start. The first part explains the advantages which E-League had for undergraduate students. The second part covers the electrical, mechanical and control parts of robot. Next part describes our development on a new Vision system using smart scanning technique. Moreover, a robust filter on variable lighting condition and path planning improvement based on potential filed algorithm. Finally, the last part introduces MRL 3D Simulator which developed to investigate the control commands. 1 Introduction The Azad University of Qazvin’s MRL RoboCup team established due to research in Mechatronics and Robotics in Mechatronics Research Laboratory. A year of hard effort leads to qualification in E-League competition. Although we missed the game but E-League experiences was a fairly good initiation to construct our small siz...

Breast cancer is the foremost common invasive cancer among ladies and is the primary cause of mor... more Breast cancer is the foremost common invasive cancer among ladies and is the primary cause of mortality from cancer around the world. To avoid the tall mortality, early detection and treatment are essential. Breast screening which uses noninvasive manner to assess tissue properties plays an imperative role in early designation. In any case, the huge information volume makes the examination become long, time-consuming and inoperable. Machine learning techniques and image processing are trending to investigate different tissue characterization and tumor appearance in radiology for automatic malignancy classification. This paper provide comparison of two supervised classification techniques for angiogenesis detection in computed tomography laser mammography image which is the major sign of high hemoglobin concentration and breast cancer.

2018 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium

Reinforcement learning is a subfield of machine learning which is similar to human learning. In r... more Reinforcement learning is a subfield of machine learning which is similar to human learning. In recent years, it has drawn a considerable portion of researchers' attention and it has been revolutionized; such as its integration with deep learning. This integration has created a better understanding of the visual environments and end-to-end direct learning from pixels to solve problems that have previously been intractable. This improvement has led to the creation of various deep reinforcement learning algorithms with different goals. In this paper, deep reinforcement learning algorithms and their applications are reviewed and categorized. This work also addresses the advantages and disadvantages of algorithms and the challenges that are solved with appearance of deep reinforcement learning. In order to use these algorithms, there are important considerations that need to be addressed in each problem. These considerations are about the most important components of reinforcement learning, which has been analyzed and categorized as the important achievement of this paper.

2018 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium

In Recent years, Representation learning as one of the information extraction and data mapping me... more In Recent years, Representation learning as one of the information extraction and data mapping methods in machine learning systems has received huge attention. Artificial deep neural networks are considered as one of the basic structures capable of representation learning. However, a large number of standard representation learning methods are supervised and requires a lot of labeled data. In this paper, we introduce an unsupervised representation learning by designing and implementing deep neural networks (DNNs) in combination with Generative Adversarial Networks (GANs). The main idea behind the proposed method, which causes the superiority of this method over others is representation learning via the generative models and encoder networks altogether. In this research, encoders are utilized in addition to the generative models to help the more features to be extracted. It is shown that the proposed method not only help feature extraction but accelerate and improve the performance of the learning in GANs which lead to better feature extraction. The results confirm the superiority of the proposed approach regarding classification accuracy by 2% to 6% improvement over other unsupervised feature learning methods.

Biomedical Signal Processing and Control

Abstract Photoplethysmography and Ballistocardiography are two concepts that are used to measure ... more Abstract Photoplethysmography and Ballistocardiography are two concepts that are used to measure heart rate from human, by using facial videos. Heart rate estimation is essential to determine the physiological and pathological state of a person. This paper presents a critical review of digital camera based heart rate estimating method on facial skin. This review extends the investigation on to the principles and theory behind photoplethysmography and ballistocardiography. The article contains reviews on the significance of the methods and contributions to overcome challenges such as; poor signal strength, illumination variance, and motion variance. The experiments were conducted to validate the state of the art methods on a challenging database that is available publicly. The implemented methods were validated using the database, on 27 subjects for a range of skin tones from pearl white, fair, olive to black. The results were computed using statistical methods such as: mean error, standard deviation, the root mean square error, Pearson correlation coefficient, and Bland-Altman analysis. The results derived from the experiments showed the reliability of the state of the art methods and provided direction to improve for situations involving illumination variance and motion variance.

Journal of digital imaging, Jan 20, 2017

Computed tomography laser mammography (Eid et al. Egyp J Radiol Nucl Med, 37(1): p. 633-643, 1) i... more Computed tomography laser mammography (Eid et al. Egyp J Radiol Nucl Med, 37(1): p. 633-643, 1) is a non-invasive imaging modality for breast cancer diagnosis, which is time-consuming and challenging for the radiologist to interpret the images. Some issues have increased the missed diagnosis of radiologists in visual manner assessment in CTLM images, such as technical reasons which are related to imaging quality and human error due to the structural complexity in appearance. The purpose of this study is to develop a computer-aided diagnosis framework to enhance the performance of radiologist in the interpretation of CTLM images. The proposed CAD system contains three main stages including segmentation of volume of interest (VOI), feature extraction and classification. A 3D Fuzzy segmentation technique has been implemented to extract the VOI. The shape and texture of angiogenesis in CTLM images are significant characteristics to differentiate malignancy or benign lesions. The 3D comp...

EXCLI journal, 2017

Breast cancer is the most prevalent cancer that affects women all over the world. Early detection... more Breast cancer is the most prevalent cancer that affects women all over the world. Early detection and treatment of breast cancer could decline the mortality rate. Some issues such as technical reasons, which related to imaging quality and human error, increase misdiagnosis of breast cancer by radiologists. Computer-aided detection systems (CADs) are developed to overcome these restrictions and have been studied in many imaging modalities for breast cancer detection in recent years. The CAD systems improve radiologists' performance in finding and discriminating between the normal and abnormal tissues. These procedures are performed only as a double reader but the absolute decisions are still made by the radiologist. In this study, the recent CAD systems for breast cancer detection on different modalities such as mammography, ultrasound, MRI, and biopsy histopathological images are introduced. The foundation of CAD systems generally consist of four stages: Pre-processing, Segmenta...

2016 6th International Conference on Intelligent and Advanced Systems (ICIAS), 2016

This paper presents a feasibility study on heart rate detection using a digital camera. The paper... more This paper presents a feasibility study on heart rate detection using a digital camera. The paper investigates the possibility of Heart rate detection for individuals far from the camera sensor. The study is done to exploit the feasibility for heart rate estimation using a digital camera to enables health monitoring in visual surveillance. An experiment was conducted using 14 healthy subjects of various skin tones. State of the art heart rate estimation methods from photoplethysmography and ballistocardiography was implemented. The method were experimented on videos of subjects that were standing away 5 meters from the camera. Results derived showed that the technology has many challenges are to be overcome. The effect of ambient light variation, involuntary artifact movement, and poor signal to noise ratio are some of the problems to be addressed.

2016 Artificial Intelligence and Robotics (IRANOPEN), 2016

Road detection from a single image is a challenging problem. In this paper, a new color feature b... more Road detection from a single image is a challenging problem. In this paper, a new color feature based on road detection method has been introduced. The proposed method utilized color features to learn and estimate the road straight part and provide vanishing points. In order to extract the road area, a combination of new learned color features and vanishing point algorithm have been used that can be released as the proposed method contribution. The experimental results show the efficiency of new method and Obtained results; Recall 92%, F-Measure 84% and accuracy 90% are compared with existing methods which show superiority of the proposed method.

2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings, 2016

This paper presents an optimal selection on the region of interest (ROI) and color spaces to extr... more This paper presents an optimal selection on the region of interest (ROI) and color spaces to extract photoplethysmography signals from facial videos. The study is carried out under two sections; ROI selection and color space selection. We compared five different ROI selection for different regions of the face. We also investigated three color spectrums namely additive, perceptual and orthogonal color spaces. The study experimented on the publicly available human-computer interaction (HCI) database. When evaluated on 30 subjects, the results showed that the ROI selection on the forehead and the green spectrum of the additive color space to provides higher accuracy for heart rate measurement.

2015 IEEE Student Symposium in Biomedical Engineering & Sciences (ISSBES), 2015

Video scene of real world crowd movement present great challenges for real-time visual surveillan... more Video scene of real world crowd movement present great challenges for real-time visual surveillance system. This paper presents a framework that detects and cluster dominant crowd flow field into region of interest from a video sequence. A particle dynamic system is applied on the video scene represented by optical flow features obtained based on classical-NL technique. Time integration of the system gives the individual particle motion trajectory. The collection of motion trajectories gives the region of interest. We obtained the segmented dominant flow regions by clustering the region of interest. The clustering of flow field may indicate the possible presence of instability in the segmented regions. Performances of different clustering techniques are compared in this study. Comparison of classification accuracy, precision, recall and F-measures are reported. Different boundaries of flow segments are detected. A change observed on segmented flow field is considered as anomaly. The experiments are carried out on publicly available datasets of crowd.

This paper presents an overview of the MRL small size robotic team. This paper describes three of... more This paper presents an overview of the MRL small size robotic team. This paper describes three of the main changes to the MRL RoboCup team which lead us to Smart Start. The first part explains the advantages which E-League had for undergraduate students. The second part covers the electrical, mechanical and control parts of robot. Next part describes our development on a new Vision system using smart scanning technique. Moreover, a robust filter on variable lighting condition and path planning improvement based on potential filed algorithm. Finally, the last part introduces MRL 3D Simulator which developed to investigate the control commands.